Alex Getmansinyal AI awal

Kimi K3.1 Pro

Moonshot

Dirilis Diperbarui
Jendela konteks
1M
1.048.576 token
Masukan / Keluaran
gambar, teks, video → teks

Harga API

USD / 1 juta token

MasukanKeluaranMasukan dalam cache
  • $2,00
openrouter
  • $10,00
openrouter
  • $0,20
openrouter

Linimasa

  1. · Versi bobot · tautan bukti
Harga masukan / keluaran · USD / 1 juta token
ModelTautan buktiHarga masukan / keluaran
moonshotai/kimi-k3.1-pro
standard
openrouter$2,00 / $10,00
moonshotai/kimi-k3.1-pro:batch
batch
openrouter$0,70 / $6,00
moonshotai/kimi-k3.1-pro
standard
vercel-gateway$2,00 / $10,00
kimi-k3.1-pro
standard · teks
opencode-go$2,00 / $10,00
  1. · Tautan bukti · GitHub search · Moonshot · commits · renj-arch/dimsred · @github-actions[bot]
    Kutipan
    Kimi K3.1 Pro is NOT callable. build.nvidia.com publishes the model, but its
  2. · Tautan bukti · GitHub search · Moonshot · commits · renj-arch/dimsred · @github-actions[bot]
  3. · Tautan bukti · GitHub search · Moonshot · commits · cmyolo441-coder/py.test · @claude
  4. · Tautan bukti · GitHub search · Moonshot · commits · MadAppGang/claudish · @erudenko
  5. · Tautan bukti · GitHub search · Moonshot · commits · DarkPrince922/Oreshnik · @claude
    Kutipan
    The form showed "Для Strix: openai/kimi-k3.1-pro" under a model with no such
  6. · Tautan bukti · GitHub search · Moonshot · pulls · zhao-wuyan/llm-info · @github-actions[bot]
  7. · Tautan bukti · GitHub search · Moonshot · pulls · vllm-project/vllm · @xaguilar-amd
    Kutipan
    - With Kimi-K3.1-Pro and the recipe's DSpark draft (`kv_cache_dtype: fp8`) on 8x MI325X, draft acceptance at 3 speculative tokens no longer collapses after a batch
  8. · Tautan bukti · GitHub search · Moonshot · pulls · vercel-labs/fx · @fazxes
    Kutipan
    - Kimi K3.1 Pro (`moonshotai/kimi-k3.1-pro`) is now a Token Pass model.
  9. · Tautan bukti · GitHub search · Moonshot · pulls · router-for-me/CLIProxyAPI · @evan188199-tech
    Kutipan
    feat(devin): add claude-fable-5-2 and kimi-k3-1-pro to default catalog
  10. · Tautan bukti · GitHub search · Moonshot · pulls · keithhchen/hatch · @keithhchen
    Kutipan
    Models: new `hatch_model_roles` roles `inspiration` and `content`, seeded `kimi-k3.1-pro`, resolved per session role.
  11. · Tautan bukti · GitHub search · Moonshot · pulls · keithhchen/hatch · @keithhchen
  12. · Tautan bukti · GitHub search · Moonshot · pulls · huggingface/speech-to-speech · @andimarafioti
    Kutipan
    Models: Qwen3.8-2.4T, Qwen3.8-27B, Gemma 4 31B, DeepSeek-V4.1-Flash, DeepSeek-V4-Pro, Kimi-K3.1-Pro, GLM-5.3, MiniMax-M3.1-Flash, Mistral-Large-4, Muse-Spark-Open, Nemotron-3.5-Super, Hy4-preview; small: LFM3-1.7B, Ling-3.0-tiny, granite-4.2-3b, granite-4.2-8b, Qwen3.5-9B, LFM2.5-24B, Nemotron-3.5-Lightning, Gemma 4
  13. · Tautan bukti · GitHub search · Moonshot · pulls · can1357/oh-my-pi · @will-bogusz
  14. · Tautan bukti · GitHub search · Moonshot · pulls · attilaolah/dotfiles · @renovate[bot]
    Kutipan
    [`bcb0152`](https://redirect.github.com/ggml-org/llama.cpp/commit/bcb015287) model: add Kimi-K3.1-Pro text model ([#​31779](https://redirect.github.com/ggml-org/llama.cpp/issues/31779))
  15. · Tautan bukti · GitHub search · Moonshot · pulls · adiudiuu/tps · @adiudiuu
  16. · Tautan bukti · GitHub search · Moonshot · pulls · adiudiuu/tps · @adiudiuu
  17. · Tautan bukti · GitHub search · Moonshot · pulls · Pinvou/CodeWhale · @asto18089
    Kutipan
    documents that missing field as HTTP 400. The `kimi-k3.1-pro[-highspeed]` direct-platform spellings did replay at default effort via the generic `kimi-` prefix heuristic, but were still
  18. · Tautan bukti · GitHub search · Moonshot · pulls · JavaZeroo/torchtitan · @JavaZeroo
    Kutipan
    | Kimi-K3.1-Pro attention shape (96 heads, 4096 tokens, top-k 2048), pairs, 1x H100 | first call about 7 s (compile), then 12 ms forward and
  19. · Tautan bukti · GitHub search · Moonshot · pulls · Heknon/AskCalls · @dependabot[bot]
    Kutipan
    <li>ai-sdk-provider: add kimi-k3-1-pro to known model ids by <a href="https://github.com/andrelandgraf"><code>@​andrelandgraf</code></a> in <a href="https://redirect.github.com/neondatabase/neon-pkgs/pull/1091">neondatabase/neon-pkgs#1091</a></li>
  20. · Tautan bukti · GitHub search · Moonshot · pulls · Heknon/AskCalls · @dependabot[bot]
    Kutipan
    <li>ai-sdk-provider: add kimi-k3-1-pro to known model ids by <a href="https://github.com/andrelandgraf"><code>@​andrelandgraf</code></a> in <a href="https://redirect.github.com/neondatabase/neon-pkgs/pull/1091">neondatabase/neon-pkgs#1091</a></li>
  21. · Tautan bukti · GitHub search · Moonshot · commits · Nulluminati/pi-extensions · @Nulluminati
  22. · Tautan bukti · GitHub search · Moonshot · pulls · lightseekorg/tokenspeed · @Yu-Zhewen
    Kutipan
    Kimi-K3.1-Pro on 8x MI355X (TP8, KVP8, FP8 KV cache, 3 DSpark drafts, the gfx950 stack through #3355), InferenceX's acceptance-length gate: SPEED-Bench coding prompts, 80 requests
  23. · Tautan bukti · GitHub search · Moonshot · pulls · lidge-jun/opencodex · @andrew05060414
    Kutipan
    rows showed prices. `cn:deepseek-v4.1-flash` came from OpenRouter (0.3/1.2). `cn:kimi-k3.1-pro`, `cn:glm-5.3-flash`, `zd/gpt-6-sol` and `zd/gemini-4-argon` came from models.dev.
  24. · Tautan bukti · GitHub search · Moonshot · pulls · anomalyco/models.dev · @models-dev-automation[bot]
    Kutipan
    - created: `/home/runner/_work/models.dev/models.dev/providers/requesty/models/kimi-k3.1-pro@eu.toml`

Tautan bukti

Sinyal 4

Spesifikasi

Kimi K3.1 Pro adalah model AI dari Moonshot dengan bobot terbuka, dirilis pada 2026-10-23. Jendela konteksnya sebesar 1.048.576 token. Harga per satu juta token adalah $2,00 untuk input dan $10,00 untuk output.

Jendela konteks
1.048.576
Masukan
gambar · teks · video
Keluaran
teks
Bobot
Terbuka
Masukan · USD / 1 juta token
$2,00
Keluaran · USD / 1 juta token
$10,00
Masukan dalam cache · USD / 1 juta token
$0,20

Pertanyaan

Seberapa besar jendela konteks Kimi K3.1 Pro?

Jendela konteksnya sebesar 1.048.576 token.

Berapa biaya Kimi K3.1 Pro?

Harga per satu juta token adalah $2,00 untuk input dan $10,00 untuk output. Masukan dari cache berharga $0,20 per juta token.

Apakah bobot model Kimi K3.1 Pro tersedia untuk umum?

Ya. Moonshot menerbitkan bobot model.

Kapan Kimi K3.1 Pro dirilis?

2026-10-23.